Milestone map
Milestone map
2 milestones
Do the phase's lessons in public
1–1 weeks (about 10 hrs/week, est)
Work through the 15 lessons of Phase 8: Generative AI from AI Engineering from Scratch (free) and keep the generative AI lessons' notebooks (autoencoders, GANs, diffusion from scratch, latent diffusion, evaluation) in one public repo as you go. About 8 hours (est).
Proof required
Link your public repo with the generative AI lessons' notebooks (autoencoders, GANs, diffusion from scratch, latent diffusion, evaluation), and show your self-check (quizzes passed, notebooks run, tests passing where they exist).
What gets checked
- Each notebook runs.
- Generated samples are saved in the repo.
- Each model is scored with the lesson's metric (FID, CLIP score).
Common mistakes
- Copying the repo's solutions: verifiers read your history and ask about your code.
- Skipping the self-check, then asking for review too early.
Powstik Guide
A public repo with the generative AI lessons' notebooks (autoencoders, GANs, diffusion from scratch, latent diffusion, evaluation).
Steps
- Make a public repo for this phase.
- Do one lesson at a time and commit after each.
- Self-check: Run each lesson's code; it must work on your machine as the lesson shows. Run each lesson's notebook top to bottom; its outputs must match the lesson.
- Write a short README: what is here and how to run it.
- Ask three people who know the topic to check it.
Template
README Phase 8: Generative AI (AI Engineering from Scratch) What is here: How to run it: Self-check result: What was hardest:
What gets sent back
- One big upload with no history.
- Self-check not shown.
- Code that does not run from the README.
Resources
Foundationstart here
Depthgo deeper
What a verifier looks for
- Each notebook runs.
- Generated samples are saved in the repo.
- Each model is scored with the lesson's metric (FID, CLIP score).
- Ask about one choice in the code; the answer should be clear.
You'll sign in first, then come straight back here.
Train a small generator
2–4 weeks (6–10 hrs/week)
Use what you learned. Make a small image or audio generator (a VAE, GAN or diffusion model) trained on a dataset you choose, with samples and FID or another stated metric. It must run, be evaluated and be documented.
Proof required
Link a small image or audio generator (a VAE, GAN or diffusion model) trained on a dataset you choose, with samples and FID or another stated metric, with a README that says how to run it and what the evaluation found.
What gets checked
- It trains from the README.
- The metric is reported and explained.
- Failure samples are shown, not only the best ones.
Common mistakes
- A demo with no evaluation.
- Numbers without the data or code that produced them.
Powstik Guide
A small image or audio generator (a VAE, GAN or diffusion model) trained on a dataset you choose, with samples and FID or another stated metric.
Steps
- Write one line: what it does and for whom.
- Build the smallest version that works.
- Write the evaluation first, then improve against it.
- Write the README with the results.
- Ask three people to check it.
Template
README What it does: How to run it: How it was evaluated: Results: Limits:
What gets sent back
- Does not run from the README.
- No evaluation.
- Claims more than the evaluation shows.
Resources
Foundationstart here
What a verifier looks for
- It trains from the README.
- The metric is reported and explained.
- Failure samples are shown, not only the best ones.
- Run it, or watch it run: it must work, be evaluated and be documented.
- Check that the work is the person's own.
You'll sign in first, then come straight back here.